Recursive LLM prompts

&quot;Foundational AI companies love this one trick&quot;<p>It&#x27;s part of why they love agents and tools like cursor -&gt; turns a problem that could&#x27;ve been one prompt and a few hundred tokens into dozens of prompts and thousands of tokens ;)

<i>The bigger picture goal here is to explore using prompts to generate new prompts</i><p>I see this as the same as a reasoning loop. This is the approach I use to quickly code up pseudo reasoning loops on local projects. Someone had asked in another thread &quot;how can I get the LLM to generate a whole book&quot;, well, just like this. If it can keep prompting itself to ask &quot;what would chapter N be?&quot; until &quot;THE END&quot;, then you get your book.

The last commit is from April 2023, should this post maybe have a (2023) tag? Two years is eons in this space.

I love this! My take on it for MCP: <a href="https:&#x2F;&#x2F;github.com&#x2F;kordless&#x2F;EvolveMCP">https:&#x2F;&#x2F;github.com&#x2F;kordless&#x2F;EvolveMCP</a>

This is kind of like a self generating agentic context.. cool. I think regular agents, especially adversarial agents, are easier to get focused on most types of problems though.<p>Still clever.

I feel that often getting LLMs to do things like mathematical problems or citation is much harder than simply writing software to achieve that same task.

Trying to save state in a non-deterministic system, not the best idea. Those things need to be externalised.

Excellent fun. Now just to create a prompt to show iterated LLMs are turing complete.

LLM quine when?

Should definitely get a date tag.